8 papers
Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective
Hongyi Fang, Chuwen Xie, Benjia Zhou +6
Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction. However, t…
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
Xiqi Hao, Zengqing Wu, Yu-Xuan Qiu +4
Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that convergence reflects genuine d…
The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment
Junyu Lu, Qi Wei, Peishuo Zheng +6
Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have already passed prosecutorial r…
GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models
Ziyang Wang, Jiangfeng Xiao, Chuan Xiao +3
Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune…
Efficient Query Rewrite Rule Discovery via Standardized Enumeration and Learning-to-Rank(extend)
Yuan Zhang, Yuxing Chen, Yuekun Yu +5
Query rewriting is essential for database performance optimization, but existing automated rule enumeration methods suffer from exponential search spaces, severe redundancy, and po…
ShapleyPipe: Hierarchical Shapley Search for Data Preparation Pipeline Construction
Jing Chang, Chang Liu, Jinbin Huang +3
Automated data preparation pipeline construction is critical for machine learning success, yet existing methods suffer from two fundamental limitations: they treat pipeline constru…